@inproceedings{fedorchenko-alumae-2025-optimizing,
    title = "Optimizing {Estonian} {TV} Subtitles with Semi-supervised Learning and {LLM}s",
    author = {Fedorchenko, Artem  and
      Alum{\"a}e, Tanel},
    editor = "Johansson, Richard  and
      Stymne, Sara",
    booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
    month = mar,
    year = "2025",
    address = "Tallinn, Estonia",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.nodalida-1.14/",
    pages = "136--141",
    ISBN = "978-9908-53-109-0",
    abstract = "This paper presents an approach for generating high-quality, same-language subtitles for Estonian TV content. We finetune the Whisper model on human-generated Estonian subtitles and enhance it with iterative pseudo-labeling and large language model (LLM) based post-editing. Our experiments demonstrate notable subtitle quality improvement through pseudo-labeling with an unlabeled dataset. We find that applying LLM-based editing at test time enhances subtitle accuracy, while its use during training does not yield further gains. This approach holds promise for creating subtitle quality close to human standard and could be extended to real-time applications."
}